Check out the new USENIX Web site. next up previous
Next: Discussion Up: Web Service Models Previous: Storage Response Time

   
Service Response Time

We combine these models to predict average total response time R for the service, deliberately ignoring congestion on the network paths to the clients (which the utility OS cannot control). Given a measure DP of average per-request service demand on the Web server CPU, CPU response time RP is given by a simple queuing model similar to the storage model above; previous work [12] illustrates use of such a model to adaptively provision CPU resources for Web services. The service's average response time R is simply:


R = RP + RS (1 - H) (5)

This ignores the CPU cost of I/O and the effects of prefetching for large files. The CPU and storage models already account (crudely) for these factors in the average case.



Ronald Doyle
2003-01-20